© 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. 92278
    Prev
    Next
    INDEX
    Explanations

    NM

    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
    thâu
    -0.52
    orphism
    -0.52
    enschaft
    -0.51
    CJK
    -0.51
    fano
    -0.50
    etton
    -0.49
    stander
    -0.48
    ABN
    -0.48
    ArgsConstructor
    -0.48
    ants
    -0.47
    POSITIVE LOGITS
     titolata
    0.64
     miles
    0.61
     vectorielles
    0.57
    miles
    0.55
    ंदीखरीदारी
    0.54
    SequentialGroup
    0.54
    ScopeManager
    0.54
     vettoriale
    0.53
     Fiche
    0.51
     validamos
    0.51
    Activations Density 0.000%

    No Known Activations