Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 14290
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and their conditions

    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
    <eos>
    -0.71
    +:+
    -0.67
    __":
    -0.58
     <<<<<<<<<<<<<<
    -0.56
    __':
    
    -0.56
    onAttach
    -0.53
    Havolalar
    -0.52
     You
    -0.51
    ulas
    -0.51
    각주
    -0.51
    POSITIVE LOGITS
     صوتيه
    0.60
     fotografi
    0.57
    født
    0.56
     Purg
    0.55
    ThroughAttribute
    0.54
     OGS
    0.54
    +#+
    0.53
    ">:
    0.52
    turnstile
    0.52
     Rouge
    0.52
    Activations Density 0.009%

    No Known Activations