© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94617
    Prev
    Next
    INDEX
    Explanations

    CVE

    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
    CVE
    -0.68
     Administrativna
    -0.61
     CVE
    -0.61
    CV
    -0.51
    pyx
    -0.50
    tagext
    -0.49
    Composable
    -0.48
     mê
    -0.47
    WithMany
    -0.47
    લી
    -0.47
    POSITIVE LOGITS
    InSection
    0.60
    mands
    0.52
    igshid
    0.52
     виправивши
    0.49
    PRWEB
    0.48
    ArgsConstructor
    0.45
    setof
    0.44
    WarningLevel
    0.43
    ffine
    0.43
    ————————————
    0.43
    Activations Density 0.011%

    No Known Activations