© 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. 5-CLT-HP
    7. 4658
    Prev
    Next
    INDEX
    Explanations

    of about

    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
    ISupport
    -0.53
    ріш
    -0.48
     kapturem
    -0.47
    __(/*!
    -0.45
    Good
    -0.45
    bucks
    -0.45
    ability
    -0.45
    lenir
    -0.45
     beginnetje
    -0.45
     bizi
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.84
    rungsseite
    0.74
    dafx
    0.65
     nakalista
    0.61
    CppMethod
    0.61
    ToTensor
    0.60
     textStatus
    0.59
    帖最后由
    0.58
    oa̍t
    0.58
     BitmapFactory
    0.58
    Activations Density 0.002%

    No Known Activations