© 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. 92581
    Prev
    Next
    INDEX
    Explanations

    Code, technical instructions

    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
    Portály
    -0.48
    enido
    -0.47
    dbo
    -0.47
    силання
    -0.45
    homonymie
    -0.45
     there
    -0.44
    moveToFirst
    -0.43
    CÓMO
    -0.43
    dragen
    -0.43
    qtype
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.76
    LookAnd
    0.60
    Населення
    0.59
    VersionUID
    0.56
    Autoritní
    0.55
    Hentet
    0.55
     صوتيه
    0.54
     فريبيس
    0.53
    ScopeManager
    0.52
    featureID
    0.52
    Activations Density 0.000%

    No Known Activations