© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6013
    Prev
    Next
    INDEX
    Explanations

    research/formal writing

    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
     صوتيه
    -0.69
    LookAnd
    -0.68
    OGND
    -0.65
    imageshack
    -0.65
    richTextPanel
    -0.65
    География
    -0.64
     thereof
    -0.63
    HandlerContext
    -0.60
     supplémentaires
    -0.60
     possesso
    -0.60
    POSITIVE LOGITS
     disambiguazione
    0.48
    lances
    0.46
    }*/
    0.43
     DBNull
    0.42
    =)
    0.40
     ब्रेकडाउन
    0.40
    GenerationType
    0.40
    ARCH
    0.40
    ])
    0.40
    voz
    0.39
    Activations Density 0.023%

    No Known Activations