© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4336
    Prev
    Next
    INDEX
    Explanations

    Engineering/mechanics

    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
    englanniksi
    -0.51
    曖昧さ回避
    -0.48
     apre
    -0.46
     lead
    -0.45
     chu
    -0.45
    MMC
    -0.43
     massa
    -0.42
    lead
    -0.42
     co
    -0.42
    CU
    -0.41
    POSITIVE LOGITS
     Efq
    0.82
    AndEndTag
    0.77
     quæ
    0.69
    glEnd
    0.68
     myſelf
    0.67
     endwhile
    0.66
    LookAnd
    0.66
     ―――――
    0.65
     animés
    0.63
     Majefty
    0.63
    Activations Density 0.000%

    No Known Activations