© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43304
    Prev
    Next
    INDEX
    Explanations

    Writings

    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
    ſelf
    -0.95
    ſelves
    -0.94
     preſent
    -0.87
     Houſe
    -0.87
     Anſ
    -0.86
     Moderato
    -0.86
     Efq
    -0.85
     myſelf
    -0.84
     beſt
    -0.84
     Eſ
    -0.84
    POSITIVE LOGITS
    ]';
    0.54
     esti
    0.50
    chapper
    0.49
     interna
    0.47
     mar
    0.46
     zu
    0.46
     enf
    0.46
     te
    0.45
    ,$_
    0.45
    VPB
    0.45
    Activations Density 0.542%

    No Known Activations