© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93669
    Prev
    Next
    INDEX
    Explanations

    For

    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
     For
    -1.28
    For
    -0.88
     FOR
    -0.77
     alatt
    -0.59
    :+:
    -0.58
     To
    -0.52
    collar
    -0.52
     Untuk
    -0.52
    ForUser
    -0.51
    bný
    -0.47
    POSITIVE LOGITS
     purpoſe
    0.82
     myſelf
    0.75
    Personensuche
    0.73
     Houſe
    0.72
     ་་
    0.70
     ✭✭
    0.69
     ſche
    0.67
    Portail
    0.67
     reaſon
    0.67
     PicClick
    0.67
    Activations Density 1.728%

    No Known Activations