© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94305
    Prev
    Next
    INDEX
    Explanations

    aim

    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
    RectangleBorder
    -0.91
    awtextra
    -0.69
     arşivlendi
    -0.68
    ISupport
    -0.65
     مشين
    -0.64
    stdc
    -0.62
    "}")
    -0.59
    PreInfinity
    -0.59
    posedge
    -0.58
    INCREF
    -0.57
    POSITIVE LOGITS
     to
    0.85
     suppress
    0.47
    ToRemove
    0.45
     isolate
    0.45
     at
    0.45
     manage
    0.45
     stabilize
    0.45
     firstly
    0.44
     eradicate
    0.44
     complémentaires
    0.43
    Activations Density 0.001%

    No Known Activations