© 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. 90955
    Prev
    Next
    INDEX
    Explanations

    by

    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
    by
    -1.45
    bin
    -0.95
    bi
    -0.90
     by
    -0.81
    ped
    -0.81
    bit
    -0.80
    bys
    -0.71
    bed
    -0.69
    py
    -0.68
    ben
    -0.67
    POSITIVE LOGITS
     Theſe
    1.28
     Monfieur
    1.25
     ―――――
    1.24
     itſelf
    1.24
     Efq
    1.23
     myſelf
    1.21
     Houſe
    1.18
    ^(@)
    1.16
     Jefus
    1.16
     Majefty
    1.13
    Activations Density 1.565%

    No Known Activations