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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40008
    Prev
    Next
    INDEX
    Explanations

    piece release

    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
    <bos>
    -0.55
     released
    -0.52
     étoient
    -0.52
     avoient
    -0.52
     mauvaises
    -0.50
     barbati
    -0.49
     pauvre
    -0.48
     embarazadas
    -0.48
     sauvages
    -0.48
     lebaran
    -0.48
    POSITIVE LOGITS
    gameserver
    0.72
    principalTable
    0.68
    Enf
    0.60
    ForType
    0.59
    tvguidetime
    0.59
    RunWith
    0.58
    randomUUID
    0.58
     Localization
    0.58
     keyCode
    0.56
     transistor
    0.55
    Activations Density 0.025%

    No Known Activations