© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93567
    Prev
    Next
    INDEX
    Explanations

    specialties

    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
     picking
    -0.60
    pick
    -0.58
    Pick
    -0.53
     Chid
    -0.52
     '{@
    -0.51
    s
    -0.47
     Pick
    -0.46
    iomanip
    -0.46
    uoti
    -0.44
     gustos
    -0.43
    POSITIVE LOGITS
     gynhyrchwyd
    0.82
     Réponses
    0.75
     nahilalakip
    0.74
    expandindo
    0.73
    awake
    0.71
     nakalista
    0.70
     snippetHide
    0.67
     bezeichneter
    0.67
     useAppContext
    0.66
    cshtml
    0.66
    Activations Density 0.803%

    No Known Activations