© 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. 97502
    Prev
    Next
    INDEX
    Explanations

    present

    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
     refusé
    -0.75
     ddelweddau
    -0.67
     feroit
    -0.67
     littéraire
    -0.66
     PLWABN
    -0.66
    ällor
    -0.66
     avoient
    -0.66
     photolibrary
    -0.65
     électroniques
    -0.65
     auffi
    -0.65
    POSITIVE LOGITS
    RectangleBorder
    0.53
    istic
    0.48
     
    0.47
    mping
    0.47
    createClass
    0.45
    rénées
    0.43
     semp
    0.41
    ForeignKey
    0.41
    ISTIC
    0.41
    AccessorTable
    0.40
    Activations Density 0.043%

    No Known Activations