© 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. 90827
    Prev
    Next
    INDEX
    Explanations

    methods

    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
    SourceChecksum
    -0.81
     виправивши
    -0.77
    Sucesor
    -0.74
    writeFieldEnd
    -0.73
    ContentAsync
    -0.73
     continúas
    -0.71
     мәкалә
    -0.70
    Portale
    -0.70
    Попис
    -0.70
     ddelweddau
    -0.68
    POSITIVE LOGITS
    짓
    0.48
     recon
    0.47
     Diff
    0.40
     identification
    0.40
    rix
    0.40
     identifying
    0.39
    züglich
    0.39
     Ermitt
    0.39
    XtraBars
    0.39
    tigas
    0.37
    Activations Density 0.026%

    No Known Activations