© 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. 25676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future intentions or plans

    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
    AutoScaleMode
    -0.73
    __':
    -0.65
     виправивши
    -0.65
     GenerationType
    -0.65
    AndroidJUnit
    -0.64
     Bioaccumulative
    -0.63
    Referencer
    -0.61
    __":
    -0.59
    UnknownFields
    -0.58
    Просто
    -0.58
    POSITIVE LOGITS
     كومونز
    0.57
    full
    0.54
     full
    0.47
    httphttps
    0.46
    Full
    0.44
    المكان
    0.43
    IntArray
    0.42
     actively
    0.42
    wirk
    0.41
     actual
    0.40
    Activations Density 0.189%

    No Known Activations