© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9703
    Prev
    Next
    INDEX
    Explanations

    instances of the character 'f' and related identification codes in data streams

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behov
    -0.57
    awtextra
    -0.56
     étoient
    -0.54
     avoient
    -0.54
     voyant
    -0.52
     صوتيه
    -0.51
     découver
    -0.51
     automatiques
    -0.50
     sauvages
    -0.50
     velkommen
    -0.50
    POSITIVE LOGITS
     nakalista
    0.88
     Normdatei
    0.82
    TagMode
    0.82
     propOrder
    0.79
     pinulongan
    0.76
     createSlice
    0.70
    SequentialGroup
    0.68
    хьтан
    0.64
    CloseOperation
    0.63
    fjspx
    0.63
    Activations Density 0.002%

    No Known Activations