© 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. 0-CLT-HP
    7. 94148
    Prev
    Next
    INDEX
    Explanations

    persed

    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
     vermelhas
    -0.81
     precisione
    -0.75
     oculto
    -0.74
     المعيارى
    -0.74
    rungsseite
    -0.73
     vectorielle
    -0.73
     escond
    -0.71
     Administrativna
    -0.71
     frequenza
    -0.69
     samarbeid
    -0.68
    POSITIVE LOGITS
    ness
    0.93
    ly
    0.84
    nya
    0.63
    ation
    0.60
    ned
    0.57
    ations
    0.55
    ning
    0.55
    NESS
    0.54
    LY
    0.53
    theless
    0.51
    Activations Density 0.125%

    No Known Activations