© 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. 5-CLT-HP
    7. 5597
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Havolalar
    -0.53
    Manbalar
    -0.53
     externi
    -0.49
     "..\..\..\
    -0.49
     taking
    -0.49
     этим
    -0.48
    gemeinden
    -0.48
     Италијани
    -0.47
    יוחד
    -0.46
    Obfuscated
    -0.46
    POSITIVE LOGITS
    ंदीखरीदारी
    0.63
    />";
    0.59
    VersionUID
    0.59
    WriteLiteral
    0.58
    InstanceState
    0.56
    extAlignment
    0.56
    utilisons
    0.54
    forName
    0.53
     consultato
    0.52
    VertexAttrib
    0.52
    Activations Density 0.007%

    No Known Activations