© 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. 42180
    Prev
    Next
    INDEX
    Explanations

    temporary

    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
     temporary
    -0.86
    stone
    -0.73
    ness
    -0.72
    ting
    -0.72
    temporary
    -0.70
    s
    -0.66
     Temporary
    -0.65
    PORARY
    -0.63
    HideFlags
    -0.61
    atility
    -0.60
    POSITIVE LOGITS
    ContentAsync
    0.82
    CppMethod
    0.67
    MemoryWarning
    0.65
    DIPSETTING
    0.63
    StructEnd
    0.59
    findpost
    0.59
    StoryboardSegue
    0.56
    IndentedString
    0.55
    tvguidetime
    0.54
     suor
    0.53
    Activations Density 0.045%

    No Known Activations