© 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. 20-CLT-HP
    7. 77574
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act-logits · 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
     snippetHide
    -0.51
    APORE
    -0.49
    estu
    -0.46
    निक
    -0.45
    igshid
    -0.44
     MotionEvent
    -0.44
    bular
    -0.44
    StartTag
    -0.43
    HtmlAttribute
    -0.43
    }();
    -0.43
    POSITIVE LOGITS
    ApiProperty
    0.56
    pecting
    0.56
    IContainer
    0.53
    Manbalar
    0.52
    spyOn
    0.51
     Cull
    0.50
    rungsseite
    0.50
     فريبيس
    0.48
     Jagd
    0.48
    Glej
    0.47
    Activations Density 0.012%

    No Known Activations