© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5618
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
     ProtoMessage
    -0.75
     points
    -0.63
     насељу
    -0.61
     Butch
    -0.58
    IsContent
    -0.57
    Datuak
    -0.56
     mapStateToProps
    -0.55
     EnglishChoose
    -0.55
     parts
    -0.53
     places
    -0.53
    POSITIVE LOGITS
    
    0.51
    AutoresizingMask
    0.51
    AndWait
    0.48
     pilotes
    0.47
    AllowAnonymous
    0.47
     ogóle
    0.47
     incapable
    0.46
    EndTag
    0.46
     därför
    0.45
     disparu
    0.44
    Activations Density 0.003%

    No Known Activations