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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95124
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerToggle
    -0.51
     الرياضيه
    -0.50
     acaso
    -0.50
    Carrière
    -0.49
    المناصب
    -0.48
    +#+
    -0.48
    Enllaces
    -0.48
    <bos>
    -0.47
    RepeatedField
    -0.47
     Toch
    -0.47
    POSITIVE LOGITS
    aarrggbb
    0.60
     AttributeSet
    0.59
     مشين
    0.58
    seamnă
    0.56
    úgó
    0.56
     Réponses
    0.53
    parsedMessage
    0.53
    postValue
    0.52
    ucksack
    0.52
     murale
    0.51
    Activations Density 0.001%

    No Known Activations