© 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. 91189
    Prev
    Next
    INDEX
    Explanations

    stories/narratives

    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
    ]")]
    -0.91
     Roskov
    -0.84
    OGND
    -0.80
    WithIOException
    -0.79
     étoient
    -0.78
     feroit
    -0.78
    Obrázky
    -0.78
     avoient
    -0.78
    AndEndTag
    -0.77
    WebVitals
    -0.76
    POSITIVE LOGITS
     yet
    0.56
     and
    0.46
    ,
    0.44
     at
    0.43
     stretch
    0.42
     &
    0.42
     bomb
    0.42
     lành
    0.41
    istic
    0.41
    y
    0.41
    Activations Density 0.001%

    No Known Activations