© 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. 95183
    Prev
    Next
    INDEX
    Explanations

    personal opinions/information

    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
    andExpect
    -0.66
    клопе
    -0.63
    libft
    -0.58
    UIControlState
    -0.58
    OpenHelper
    -0.56
    jsonwebtoken
    -0.55
    #+#
    -0.54
    astify
    -0.53
    URLException
    -0.52
    lée
    -0.51
    POSITIVE LOGITS
    ?
    0.61
     "
    0.56
     historically
    0.56
     really
    0.56
     aren
    0.52
    Standards
    0.52
     kidding
    0.51
     Countess
    0.51
     "¿
    0.50
     REALLY
    0.50
    Activations Density 0.084%

    No Known Activations