© 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. 1-CLT-HP
    7. 14375
    Prev
    Next
    INDEX
    Explanations

    import

    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
    abestanden
    -0.76
    SourceChecksum
    -0.71
     esternos
    -0.70
    LookAnd
    -0.67
     resourceCulture
    -0.66
    tagext
    -0.66
    WriteTagHelper
    -0.65
     lenker
    -0.63
    Према
    -0.60
     kaarangay
    -0.59
    POSITIVE LOGITS
    ']}
    0.54
    AndEndTag
    0.53
    paraiso
    0.53
    "]}
    0.53
    "]];
    0.51
    '))
    0.51
    schra
    0.51
     пользователь
    0.49
    setDo
    0.49
    "))
    0.48
    Activations Density 6.634%

    No Known Activations