© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92173
    Prev
    Next
    INDEX
    Explanations

    declining

    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
    als
    -1.97
    ALS
    -1.45
    alling
    -1.41
    alls
    -1.08
    alled
    -0.95
    Als
    -0.76
    ials
    -0.72
    IALS
    -0.71
    alse
    -0.70
     als
    -0.69
    POSITIVE LOGITS
     himſelf
    1.26
     Efq
    1.16
     myſelf
    1.16
     Theſe
    1.15
     themſelves
    1.13
     Houſe
    1.10
     itſelf
    1.09
     uſed
    1.02
     whoſe
    1.01
    principalColumn
    1.00
    Activations Density 0.382%

    No Known Activations