© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    code and authors

    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
    Negative Logits
    +#+#
    -0.91
     betweenstory
    -0.67
    saraba
    -0.65
    BASEPATH
    -0.63
     BorderSide
    -0.61
    ActionCreators
    -0.60
     mắn
    -0.60
    irical
    -0.56
    WebElementEntity
    -0.56
     محفوظة
    -0.56
    POSITIVE LOGITS
    ArgsConstructor
    0.57
    SDG
    0.43
    "]));
    0.42
     MAS
    0.40
    titled
    0.40
     humanity
    0.38
    TableHead
    0.38
    lock
    0.38
    esac
    0.38
    WriteLine
    0.38
    Activations Density 0.001%

    No Known Activations