© 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. 42948
    Prev
    Next
    INDEX
    Explanations

    is

    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
     surla
    -0.75
    <bos>
    -0.71
     Roskov
    -0.62
    +#+
    -0.57
    jspx
    -0.55
     дописавши
    -0.55
     betweenstory
    -0.54
    InitVars
    -0.54
    ")));
    -0.53
    ionization
    -0.52
    POSITIVE LOGITS
     MotionEvent
    0.53
     Recuperado
    0.52
    SequentialGroup
    0.52
     displayed
    0.51
    addGap
    0.48
    CodeAnalysis
    0.48
    thenReturn
    0.47
    itiva
    0.47
     plateforme
    0.46
    enumii
    0.46
    Activations Density 0.088%

    No Known Activations