© 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. 90991
    Prev
    Next
    INDEX
    Explanations

    Wake

    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
    <bos>
    -0.82
    ftagPool
    -0.49
    Przypisy
    -0.43
    ysław
    -0.39
    CWE
    -0.38
     sakit
    -0.38
     dangere
    -0.37
    Q
    -0.37
    hi
    -0.36
    x
    -0.36
    POSITIVE LOGITS
    #+#
    0.81
     Chum
    0.68
    
    0.68
     Pasha
    0.67
    󠁢
    0.67
     Kig
    0.65
    argout
    0.64
    ViewInit
    0.62
    :+:
    0.61
    Портали
    0.59
    Activations Density 0.017%

    No Known Activations