© 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. 1-CLT-HP
    7. 10005
    Prev
    Next
    INDEX
    Explanations

    Strauss

    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
     Roskov
    -0.60
     autorytatywna
    -0.56
    Билгалдахарш
    -0.53
     Wikimedijinoj
    -0.50
    ilane
    -0.49
    AndEndTag
    -0.48
     OFDb
    -0.46
    elemField
    -0.46
    carpa
    -0.46
    celand
    -0.46
    POSITIVE LOGITS
     تانيه
    0.56
    utuhkan
    0.52
    gill
    0.52
     Públicas
    0.51
    RIM
    0.51
    PRWEB
    0.50
    /**
    0.50
     SwitchCompat
    0.50
     JADX
    0.48
    MENAFN
    0.48
    Activations Density 0.023%

    No Known Activations