© 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. 1-CLT-HP
    7. 15384
    Prev
    Next
    INDEX
    Explanations

    learning

    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
    ftagPool
    -0.75
     propOrder
    -0.75
    InjectAttribute
    -0.73
     Roskov
    -0.61
    copg
    -0.60
     AttributeSet
    -0.58
    ConstraintMaker
    -0.57
    IContainer
    -0.56
    ScopeManager
    -0.56
    TemporalType
    -0.55
    POSITIVE LOGITS
     new
    0.55
    توض
    0.53
     falsche
    0.52
     arbitrage
    0.51
     contingencies
    0.51
     deceleration
    0.50
    apd
    0.50
     Diſ
    0.50
    pirable
    0.50
     DD
    0.50
    Activations Density 0.008%

    No Known Activations